INDEX
Explanations
mentions of the word "vice" along with a number
references to the title "vice president."
New Auto-Interp
Negative Logits
anwhile
-0.75
Brist
-0.71
itsch
-0.68
ONES
-0.67
wana
-0.67
alon
-0.66
GOODMAN
-0.65
onian
-0.65
iary
-0.64
ambo
-0.64
POSITIVE LOGITS
versa
1.64
hum
0.86
ners
0.84
ratulations
0.79
ned
0.78
quel
0.75
iors
0.73
mire
0.72
heading
0.72
presidential
0.72
Activations Density 0.009%